caa a22 4500 475800974 CHVBK 20180406123737.0 cr unu---uuuuu 170329e20001001xx s 000 0 eng 10.1023/A:1009645229062 doi (NATIONALLICENCE)springer-10.1023/A:1009645229062 Embedding Connectionist Autonomous Agents in Time: The ‘Road Sign Problem' [Elektronische Daten] [R. Rylatt, C. Czarnecki] This paper identifies a problem of significance for approaches to adaptive autonomous agent research seeking to go beyond reactive behaviour without resorting to hybrid solutions. The feasibility of recurrent neural network solutions are discussed and compared in the light of experiments designed to test ability to handle long-term temporal dependencies, in a more situated context than hitherto. It is concluded that a general-purpose recurrent network with some processing enhancements can begin to fulfil the requirements of this non-trivial problem. Kluwer Academic Publishers, 2000 autonomous agents nationallicence recurrent neural networks nationallicence Rylatt R. Department of Computer Science, De Montfort University, Leicester, U.K. aut Czarnecki C. Department of Computer Science, De Montfort University, Leicester, U.K. aut Neural Processing Letters Kluwer Academic Publishers 12/2(2000-10-01), 145-158 1370-4621 12:2<145 2000 12 11063 https://doi.org/10.1023/A:1009645229062 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1023/A:1009645229062 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Rylatt R. Department of Computer Science, De Montfort University, Leicester, U.K aut NATIONALLICENCE 700 1- Czarnecki C. Department of Computer Science, De Montfort University, Leicester, U.K aut NATIONALLICENCE 773 0- Neural Processing Letters Kluwer Academic Publishers 12/2(2000-10-01), 145-158 1370-4621 12:2<145 2000 12 11063 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer